[PATCH v2] drm/i915/vlv: Added a rendering specific Hw WA 'WaSendDummy3dPrimitveAfterSetContext'

[PATCH v2] drm/i915/vlv: Added a rendering specific Hw WA 'WaSendDummy3dPrimitveAfterSetContext'

[akash.goel]

From: Akash Goel <akash.goel@intel.com>

This workaround is needed on VLV for the HW context feature.
It is used after adding the mi_set_context command in ring buffer
for Hw context switch. As per the spec
"The software must send a pipe_control with a CS stall and a post sync
operation and then a dummy DRAW after every MI_SET_CONTEXT and after any
PIPELINE_SELECT that is enabling 3D mode".

v2: Modified the WA comment. (Ville)

Signed-off-by: Akash Goel <akash.goel@intel.com>
---
 drivers/gpu/drm/i915/i915_gem_context.c | 65 ++++++++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/i915_reg.h         |  3 ++
 drivers/gpu/drm/i915/intel_ringbuffer.c |  9 +++++
 drivers/gpu/drm/i915/intel_ringbuffer.h |  1 +
 4 files changed, 76 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 19fd362..bc2868d 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -541,6 +541,58 @@ i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id)
 	return ctx;
 }
 
+static inline void
+mi_set_context_dummy3d_prim_wa(struct intel_ring_buffer *ring)
+{
+	u32 scratch_addr;
+	u32 flags = 0;
+
+	/*
+	 * Check if we have the scratch page allocated needed
+	 * for the Pipe Control command, otherwise don't apply
+	 * the dummmy 3d primitive workaround & add NOOPs instead
+	 */
+	if (get_pipe_control_scratch_addr(ring)) {
+		/* Actual scratch location is at 128 bytes offset */
+		scratch_addr = get_pipe_control_scratch_addr(ring) + 128;
+
+		/*
+		 * WaSendDummy3dPrimitveAfterSetContext
+		 * Software must send a pipe_control with a CS stall
+		 * and a post sync operation and then a dummy DRAW after
+		 * every MI_SET_CONTEXT and after any PIPELINE_SELECT that
+		 * is enabling 3D mode. A dummy draw is a 3DPRIMITIVE command
+		 * with Indirect Parameter Enable set to 0, UAV Coherency
+		 * Required set to 0, Predicate Enable set to 0,
+		 * End Offset Enable set to 0, and Vertex Count Per Instance
+		 * set to 0, All other parameters are a don't care.
+		 */
+
+		/*
+		 * Add a pipe control with CS Stall and postsync op
+		 * before dummy 3D_PRIMITIVE
+		 */
+		flags |= PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_CS_STALL;
+		intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4));
+		intel_ring_emit(ring, flags);
+		intel_ring_emit(ring, scratch_addr | PIPE_CONTROL_GLOBAL_GTT);
+		intel_ring_emit(ring, 0);
+
+		/* Add a dummy 3D_PRIMITVE */
+	intel_ring_emit(ring, GFX_OP_3DPRIMITIVE());
+		intel_ring_emit(ring, 4); /* PrimTopoType*/
+		intel_ring_emit(ring, 0); /* VertexCountPerInstance */
+		intel_ring_emit(ring, 0); /* StartVertexLocation */
+		intel_ring_emit(ring, 0); /* InstanceCount */
+		intel_ring_emit(ring, 0); /* StartInstanceLocation */
+		intel_ring_emit(ring, 0); /* BaseVertexLocation  */
+	} else {
+		int i;
+		for (i = 0; i < 11; i++)
+			intel_ring_emit(ring, MI_NOOP);
+	}
+}
+
 static inline int
 mi_set_context(struct intel_ring_buffer *ring,
 	       struct i915_hw_context *new_context,
@@ -559,7 +611,10 @@ mi_set_context(struct intel_ring_buffer *ring,
 			return ret;
 	}
 
-	ret = intel_ring_begin(ring, 6);
+	if (IS_VALLEYVIEW(ring->dev))
+		ret = intel_ring_begin(ring, 6+4+8);
+	else
+		ret = intel_ring_begin(ring, 6);
 	if (ret)
 		return ret;
 
@@ -583,7 +638,13 @@ mi_set_context(struct intel_ring_buffer *ring,
 	intel_ring_emit(ring, MI_NOOP);
 
 	if (IS_GEN7(ring->dev))
-		intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
+		if (IS_VALLEYVIEW(ring->dev)) {
+			/* FIXME, should also apply to ivb */
+			mi_set_context_dummy3d_prim_wa(ring);
+			intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
+			intel_ring_emit(ring, MI_NOOP);
+		} else
+			intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
 	else
 		intel_ring_emit(ring, MI_NOOP);
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f73a49d..9a1fee6 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -335,6 +335,9 @@
 #define   PIPE_CONTROL_DEPTH_CACHE_FLUSH		(1<<0)
 #define   PIPE_CONTROL_GLOBAL_GTT (1<<2) /* in addr dword */
 
+#define GFX_OP_3DPRIMITIVE()              \
+	((0x3<<29)|(0x3<<27)|(0x3<<24)|       \
+	 (0x0<<16)|(0x0<<10)|(0x0<<8)|(7-2))
 
 /*
  * Reset registers
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 0d7d927b..812039a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -556,6 +556,15 @@ err:
 	return ret;
 }
 
+u32
+get_pipe_control_scratch_addr(struct intel_ring_buffer *ring)
+{
+	if (ring->scratch.obj == NULL)
+		return 0;
+
+	return ring->scratch.gtt_offset;
+}
+
 static int init_render_ring(struct intel_ring_buffer *ring)
 {
 	struct drm_device *dev = ring->dev;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 38c757e..6c52d59 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -259,6 +259,7 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev);
 
 u32 intel_ring_get_active_head(struct intel_ring_buffer *ring);
 void intel_ring_setup_status_page(struct intel_ring_buffer *ring);
+u32 get_pipe_control_scratch_addr(struct intel_ring_buffer *ring);
 
 static inline u32 intel_ring_get_tail(struct intel_ring_buffer *ring)
 {
-- 
1.8.5.2

Re: [PATCH v2] drm/i915/vlv: Added a rendering specific Hw WA 'WaSendDummy3dPrimitveAfterSetContext'

[Daniel Vetter]

On Sat, Feb 08, 2014 at 02:22:12PM +0530, akash.goel@intel.com wrote:
> From: Akash Goel <akash.goel@intel.com>
> 
> This workaround is needed on VLV for the HW context feature.
> It is used after adding the mi_set_context command in ring buffer
> for Hw context switch. As per the spec
> "The software must send a pipe_control with a CS stall and a post sync
> operation and then a dummy DRAW after every MI_SET_CONTEXT and after any
> PIPELINE_SELECT that is enabling 3D mode".
> 
> v2: Modified the WA comment. (Ville)
> 
> Signed-off-by: Akash Goel <akash.goel@intel.com>

Hm, why the resend of these two patches? I don't see any changes compared
to the orignally posted v2 ...
-Daniel

> ---
>  drivers/gpu/drm/i915/i915_gem_context.c | 65 ++++++++++++++++++++++++++++++++-
>  drivers/gpu/drm/i915/i915_reg.h         |  3 ++
>  drivers/gpu/drm/i915/intel_ringbuffer.c |  9 +++++
>  drivers/gpu/drm/i915/intel_ringbuffer.h |  1 +
>  4 files changed, 76 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index 19fd362..bc2868d 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -541,6 +541,58 @@ i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id)
>  	return ctx;
>  }
>  
> +static inline void
> +mi_set_context_dummy3d_prim_wa(struct intel_ring_buffer *ring)
> +{
> +	u32 scratch_addr;
> +	u32 flags = 0;
> +
> +	/*
> +	 * Check if we have the scratch page allocated needed
> +	 * for the Pipe Control command, otherwise don't apply
> +	 * the dummmy 3d primitive workaround & add NOOPs instead
> +	 */
> +	if (get_pipe_control_scratch_addr(ring)) {
> +		/* Actual scratch location is at 128 bytes offset */
> +		scratch_addr = get_pipe_control_scratch_addr(ring) + 128;
> +
> +		/*
> +		 * WaSendDummy3dPrimitveAfterSetContext
> +		 * Software must send a pipe_control with a CS stall
> +		 * and a post sync operation and then a dummy DRAW after
> +		 * every MI_SET_CONTEXT and after any PIPELINE_SELECT that
> +		 * is enabling 3D mode. A dummy draw is a 3DPRIMITIVE command
> +		 * with Indirect Parameter Enable set to 0, UAV Coherency
> +		 * Required set to 0, Predicate Enable set to 0,
> +		 * End Offset Enable set to 0, and Vertex Count Per Instance
> +		 * set to 0, All other parameters are a don't care.
> +		 */
> +
> +		/*
> +		 * Add a pipe control with CS Stall and postsync op
> +		 * before dummy 3D_PRIMITIVE
> +		 */
> +		flags |= PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_CS_STALL;
> +		intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4));
> +		intel_ring_emit(ring, flags);
> +		intel_ring_emit(ring, scratch_addr | PIPE_CONTROL_GLOBAL_GTT);
> +		intel_ring_emit(ring, 0);
> +
> +		/* Add a dummy 3D_PRIMITVE */
> +	intel_ring_emit(ring, GFX_OP_3DPRIMITIVE());
> +		intel_ring_emit(ring, 4); /* PrimTopoType*/
> +		intel_ring_emit(ring, 0); /* VertexCountPerInstance */
> +		intel_ring_emit(ring, 0); /* StartVertexLocation */
> +		intel_ring_emit(ring, 0); /* InstanceCount */
> +		intel_ring_emit(ring, 0); /* StartInstanceLocation */
> +		intel_ring_emit(ring, 0); /* BaseVertexLocation  */
> +	} else {
> +		int i;
> +		for (i = 0; i < 11; i++)
> +			intel_ring_emit(ring, MI_NOOP);
> +	}
> +}
> +
>  static inline int
>  mi_set_context(struct intel_ring_buffer *ring,
>  	       struct i915_hw_context *new_context,
> @@ -559,7 +611,10 @@ mi_set_context(struct intel_ring_buffer *ring,
>  			return ret;
>  	}
>  
> -	ret = intel_ring_begin(ring, 6);
> +	if (IS_VALLEYVIEW(ring->dev))
> +		ret = intel_ring_begin(ring, 6+4+8);
> +	else
> +		ret = intel_ring_begin(ring, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -583,7 +638,13 @@ mi_set_context(struct intel_ring_buffer *ring,
>  	intel_ring_emit(ring, MI_NOOP);
>  
>  	if (IS_GEN7(ring->dev))
> -		intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
> +		if (IS_VALLEYVIEW(ring->dev)) {
> +			/* FIXME, should also apply to ivb */
> +			mi_set_context_dummy3d_prim_wa(ring);
> +			intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
> +			intel_ring_emit(ring, MI_NOOP);
> +		} else
> +			intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
>  	else
>  		intel_ring_emit(ring, MI_NOOP);
>  
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index f73a49d..9a1fee6 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -335,6 +335,9 @@
>  #define   PIPE_CONTROL_DEPTH_CACHE_FLUSH		(1<<0)
>  #define   PIPE_CONTROL_GLOBAL_GTT (1<<2) /* in addr dword */
>  
> +#define GFX_OP_3DPRIMITIVE()              \
> +	((0x3<<29)|(0x3<<27)|(0x3<<24)|       \
> +	 (0x0<<16)|(0x0<<10)|(0x0<<8)|(7-2))
>  
>  /*
>   * Reset registers
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 0d7d927b..812039a 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -556,6 +556,15 @@ err:
>  	return ret;
>  }
>  
> +u32
> +get_pipe_control_scratch_addr(struct intel_ring_buffer *ring)
> +{
> +	if (ring->scratch.obj == NULL)
> +		return 0;
> +
> +	return ring->scratch.gtt_offset;
> +}
> +
>  static int init_render_ring(struct intel_ring_buffer *ring)
>  {
>  	struct drm_device *dev = ring->dev;
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 38c757e..6c52d59 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -259,6 +259,7 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev);
>  
>  u32 intel_ring_get_active_head(struct intel_ring_buffer *ring);
>  void intel_ring_setup_status_page(struct intel_ring_buffer *ring);
> +u32 get_pipe_control_scratch_addr(struct intel_ring_buffer *ring);
>  
>  static inline u32 intel_ring_get_tail(struct intel_ring_buffer *ring)
>  {
> -- 
> 1.8.5.2
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx

-- 
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch

Re: [PATCH v2] drm/i915/vlv: Added a rendering specific Hw WA 'WaSendDummy3dPrimitveAfterSetContext'

[Ben Widawsky]

On Sat, Feb 08, 2014 at 02:22:12PM +0530, akash.goel@intel.com wrote:
> From: Akash Goel <akash.goel@intel.com>
> 
> This workaround is needed on VLV for the HW context feature.
> It is used after adding the mi_set_context command in ring buffer
> for Hw context switch. As per the spec
> "The software must send a pipe_control with a CS stall and a post sync
> operation and then a dummy DRAW after every MI_SET_CONTEXT and after any
> PIPELINE_SELECT that is enabling 3D mode".

Does this cause a hang? Please mention so if it does.

And for my curiosity, have we actually seen this fix anything in the
wild (also nice to have in the commit message for potential backports)?

> 
> v2: Modified the WA comment. (Ville)
> 
> Signed-off-by: Akash Goel <akash.goel@intel.com>
> ---
>  drivers/gpu/drm/i915/i915_gem_context.c | 65 ++++++++++++++++++++++++++++++++-
>  drivers/gpu/drm/i915/i915_reg.h         |  3 ++
>  drivers/gpu/drm/i915/intel_ringbuffer.c |  9 +++++
>  drivers/gpu/drm/i915/intel_ringbuffer.h |  1 +
>  4 files changed, 76 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index 19fd362..bc2868d 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -541,6 +541,58 @@ i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id)
>  	return ctx;
>  }
>  
> +static inline void
> +mi_set_context_dummy3d_prim_wa(struct intel_ring_buffer *ring)
> +{
> +	u32 scratch_addr;
> +	u32 flags = 0;
> +
> +	/*
> +	 * Check if we have the scratch page allocated needed
> +	 * for the Pipe Control command, otherwise don't apply
> +	 * the dummmy 3d primitive workaround & add NOOPs instead
> +	 */
> +	if (get_pipe_control_scratch_addr(ring)) {
> +		/* Actual scratch location is at 128 bytes offset */
> +		scratch_addr = get_pipe_control_scratch_addr(ring) + 128;
> +
> +		/*
> +		 * WaSendDummy3dPrimitveAfterSetContext
> +		 * Software must send a pipe_control with a CS stall
> +		 * and a post sync operation and then a dummy DRAW after
> +		 * every MI_SET_CONTEXT and after any PIPELINE_SELECT that
> +		 * is enabling 3D mode. A dummy draw is a 3DPRIMITIVE command
> +		 * with Indirect Parameter Enable set to 0, UAV Coherency
> +		 * Required set to 0, Predicate Enable set to 0,
> +		 * End Offset Enable set to 0, and Vertex Count Per Instance
> +		 * set to 0, All other parameters are a don't care.
> +		 */
> +
> +		/*
> +		 * Add a pipe control with CS Stall and postsync op
> +		 * before dummy 3D_PRIMITIVE
> +		 */
> +		flags |= PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_CS_STALL;
> +		intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4));
> +		intel_ring_emit(ring, flags);
> +		intel_ring_emit(ring, scratch_addr | PIPE_CONTROL_GLOBAL_GTT);
> +		intel_ring_emit(ring, 0);
> +
> +		/* Add a dummy 3D_PRIMITVE */
> +	intel_ring_emit(ring, GFX_OP_3DPRIMITIVE());
> +		intel_ring_emit(ring, 4); /* PrimTopoType*/
> +		intel_ring_emit(ring, 0); /* VertexCountPerInstance */
> +		intel_ring_emit(ring, 0); /* StartVertexLocation */
> +		intel_ring_emit(ring, 0); /* InstanceCount */
> +		intel_ring_emit(ring, 0); /* StartInstanceLocation */
> +		intel_ring_emit(ring, 0); /* BaseVertexLocation  */
> +	} else {
> +		int i;
> +		for (i = 0; i < 11; i++)
> +			intel_ring_emit(ring, MI_NOOP);
> +	}
> +}
> +
>  static inline int
>  mi_set_context(struct intel_ring_buffer *ring,
>  	       struct i915_hw_context *new_context,
> @@ -559,7 +611,10 @@ mi_set_context(struct intel_ring_buffer *ring,
>  			return ret;
>  	}
>  
> -	ret = intel_ring_begin(ring, 6);
> +	if (IS_VALLEYVIEW(ring->dev))
> +		ret = intel_ring_begin(ring, 6+4+8);
> +	else
> +		ret = intel_ring_begin(ring, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -583,7 +638,13 @@ mi_set_context(struct intel_ring_buffer *ring,
>  	intel_ring_emit(ring, MI_NOOP);
>  
>  	if (IS_GEN7(ring->dev))
> -		intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
> +		if (IS_VALLEYVIEW(ring->dev)) {
> +			/* FIXME, should also apply to ivb */
> +			mi_set_context_dummy3d_prim_wa(ring);
> +			intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
> +			intel_ring_emit(ring, MI_NOOP);
> +		} else
> +			intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
>  	else
>  		intel_ring_emit(ring, MI_NOOP);
>  
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index f73a49d..9a1fee6 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -335,6 +335,9 @@
>  #define   PIPE_CONTROL_DEPTH_CACHE_FLUSH		(1<<0)
>  #define   PIPE_CONTROL_GLOBAL_GTT (1<<2) /* in addr dword */
>  
> +#define GFX_OP_3DPRIMITIVE()              \
> +	((0x3<<29)|(0x3<<27)|(0x3<<24)|       \
> +	 (0x0<<16)|(0x0<<10)|(0x0<<8)|(7-2))
>  
>  /*
>   * Reset registers
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 0d7d927b..812039a 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -556,6 +556,15 @@ err:
>  	return ret;
>  }
>  
> +u32
> +get_pipe_control_scratch_addr(struct intel_ring_buffer *ring)
> +{
> +	if (ring->scratch.obj == NULL)
> +		return 0;
> +
> +	return ring->scratch.gtt_offset;
> +}
> +
>  static int init_render_ring(struct intel_ring_buffer *ring)
>  {
>  	struct drm_device *dev = ring->dev;
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 38c757e..6c52d59 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -259,6 +259,7 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev);
>  
>  u32 intel_ring_get_active_head(struct intel_ring_buffer *ring);
>  void intel_ring_setup_status_page(struct intel_ring_buffer *ring);
> +u32 get_pipe_control_scratch_addr(struct intel_ring_buffer *ring);
>  
>  static inline u32 intel_ring_get_tail(struct intel_ring_buffer *ring)
>  {
> -- 
> 1.8.5.2
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx

-- 
Ben Widawsky, Intel Open Source Technology Center

[PATCH v3] drm/i915/vlv: Added a rendering specific Hw WA 'WaSendDummy3dPrimitveAfterSetContext'

[sourab.gupta]

From: Akash Goel <akash.goel@intel.com>

This workaround is needed on VLV for the HW context feature.
It is used after adding the mi_set_context command in ring buffer
for Hw context switch. As per the spec
"The software must send a pipe_control with a CS stall and a post sync
operation and then a dummy DRAW after every MI_SET_CONTEXT and after any
PIPELINE_SELECT that is enabling 3D mode".

v2: Modified the WA comment. (Ville)

v3: Added the vlv identifier with the WA name

Signed-off-by: Akash Goel <akash.goel@intel.com>
Signed-off-by: Sourab Gupta <sourab.gupta@intel.com>
---
 drivers/gpu/drm/i915/i915_gem_context.c | 65 ++++++++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/i915_reg.h         |  3 ++
 drivers/gpu/drm/i915/intel_ringbuffer.c |  9 +++++
 drivers/gpu/drm/i915/intel_ringbuffer.h |  1 +
 4 files changed, 76 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index b5a5837..d09d9e3 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -583,6 +583,58 @@ i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id)
 	return ctx;
 }
 
+static inline void
+mi_set_context_dummy3d_prim_wa(struct intel_ring_buffer *ring)
+{
+	u32 scratch_addr;
+	u32 flags = 0;
+
+	/*
+	 * Check if we have the scratch page allocated needed
+	 * for the Pipe Control command, otherwise don't apply
+	 * the dummmy 3d primitive workaround & add NOOPs instead
+	 */
+	if (get_pipe_control_scratch_addr(ring)) {
+		/* Actual scratch location is at 128 bytes offset */
+		scratch_addr = get_pipe_control_scratch_addr(ring) + 128;
+
+		/*
+		 * WaSendDummy3dPrimitveAfterSetContext:vlv
+		 * Software must send a pipe_control with a CS stall
+		 * and a post sync operation and then a dummy DRAW after
+		 * every MI_SET_CONTEXT and after any PIPELINE_SELECT that
+		 * is enabling 3D mode. A dummy draw is a 3DPRIMITIVE command
+		 * with Indirect Parameter Enable set to 0, UAV Coherency
+		 * Required set to 0, Predicate Enable set to 0,
+		 * End Offset Enable set to 0, and Vertex Count Per Instance
+		 * set to 0, All other parameters are a don't care.
+		 */
+
+		/*
+		 * Add a pipe control with CS Stall and postsync op
+		 * before dummy 3D_PRIMITIVE
+		 */
+		flags |= PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_CS_STALL;
+		intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4));
+		intel_ring_emit(ring, flags);
+		intel_ring_emit(ring, scratch_addr | PIPE_CONTROL_GLOBAL_GTT);
+		intel_ring_emit(ring, 0);
+
+		/* Add a dummy 3D_PRIMITVE */
+	intel_ring_emit(ring, GFX_OP_3DPRIMITIVE());
+		intel_ring_emit(ring, 4); /* PrimTopoType*/
+		intel_ring_emit(ring, 0); /* VertexCountPerInstance */
+		intel_ring_emit(ring, 0); /* StartVertexLocation */
+		intel_ring_emit(ring, 0); /* InstanceCount */
+		intel_ring_emit(ring, 0); /* StartInstanceLocation */
+		intel_ring_emit(ring, 0); /* BaseVertexLocation  */
+	} else {
+		int i;
+		for (i = 0; i < 11; i++)
+			intel_ring_emit(ring, MI_NOOP);
+	}
+}
+
 static inline int
 mi_set_context(struct intel_ring_buffer *ring,
 	       struct i915_hw_context *new_context,
@@ -601,7 +653,10 @@ mi_set_context(struct intel_ring_buffer *ring,
 			return ret;
 	}
 
-	ret = intel_ring_begin(ring, 6);
+	if (IS_VALLEYVIEW(ring->dev))
+		ret = intel_ring_begin(ring, 6+4+8);
+	else
+		ret = intel_ring_begin(ring, 6);
 	if (ret)
 		return ret;
 
@@ -625,7 +680,13 @@ mi_set_context(struct intel_ring_buffer *ring,
 	intel_ring_emit(ring, MI_NOOP);
 
 	if (IS_GEN7(ring->dev))
-		intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
+		if (IS_VALLEYVIEW(ring->dev)) {
+			/* FIXME, should also apply to ivb */
+			mi_set_context_dummy3d_prim_wa(ring);
+			intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
+			intel_ring_emit(ring, MI_NOOP);
+		} else
+			intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
 	else
 		intel_ring_emit(ring, MI_NOOP);
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 6174fda..52f5899 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -347,6 +347,9 @@
 #define   PIPE_CONTROL_DEPTH_CACHE_FLUSH		(1<<0)
 #define   PIPE_CONTROL_GLOBAL_GTT (1<<2) /* in addr dword */
 
+#define GFX_OP_3DPRIMITIVE()              \
+	((0x3<<29)|(0x3<<27)|(0x3<<24)|       \
+	 (0x0<<16)|(0x0<<10)|(0x0<<8)|(7-2))
 
 /*
  * Reset registers
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 4eb3e06..da64255 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -560,6 +560,15 @@ err:
 	return ret;
 }
 
+u32
+get_pipe_control_scratch_addr(struct intel_ring_buffer *ring)
+{
+	if (ring->scratch.obj == NULL)
+		return 0;
+
+	return ring->scratch.gtt_offset;
+}
+
 static int init_render_ring(struct intel_ring_buffer *ring)
 {
 	struct drm_device *dev = ring->dev;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index f11ceb2..640c56d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -294,6 +294,7 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev);
 
 u32 intel_ring_get_active_head(struct intel_ring_buffer *ring);
 void intel_ring_setup_status_page(struct intel_ring_buffer *ring);
+u32 get_pipe_control_scratch_addr(struct intel_ring_buffer *ring);
 
 static inline u32 intel_ring_get_tail(struct intel_ring_buffer *ring)
 {
-- 
1.8.5.1